A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation

Abstract

Estimating count and density maps from crowd images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning. In addition, techniques developed for crowd counting can be applied to related tasks in other fields of study such as cell microscopy, vehicle counting and environmental survey. The task of crowd counting and density map estimation is riddled with many challenges such as occlusions, non-uniform density, intra-scene and inter-scene variations in scale and perspective. Nevertheless, over the last few years, crowd count analysis has evolved from earlier methods that are often limited to small variations in crowd density and scales to the current state-of-the-art methods that have developed the ability to perform successfully on a wide range of scenarios. The success of crowd counting methods in the recent years can be largely attributed to deep learning and publications of challenging datasets. In this paper, we provide a comprehensive survey of recent Convolutional Neural Network (CNN) based approaches that have demonstrated significant improvements over earlier methods that rely largely on hand-crafted representations. First, we briefly review the pioneering methods that use hand-crafted representations and then we delve in detail into the deep learning-based approaches and recently published datasets. Furthermore, we discuss the merits and drawbacks of existing CNN-based approaches and identify promising avenues of research in this rapidly evolving field.

16 pages, 17 figures

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Statistical physics of social dynamics
• Fully Convolutional Networks for Semantic Segmentation
• Crowded Scene Analysis: A Survey
• Convolutional Neural Networks Applied to House Numbers Digit Classification
• Fully Convolutional Neural Networks for Crowd Segmentation
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting
• Crowd Simulation Modeling Applied to Emergency and Evacuation Simulations using Multi-Agent Systems

Cited by in corpus (19)

• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• Crowd counting with crowd attention convolutional neural network
• Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
• Density-based clustering with fully-convolutional networks for crowd flow detection from drones
• MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery
• Counting and Segmenting Sorghum Heads
• Crowd counting with segmentation attention convolutional neural network
• Structured Inhomogeneous Density Map Learning for Crowd Counting
• Single Image Human Proxemics Estimation for Visual Social Distancing
• Crowd Density Forecasting by Modeling Patch-based Dynamics
• Exploit the potential of Multi-column architecture for Crowd Counting
• Overcoming Statistical Shortcuts for Open-ended Visual Counting
• Mask-aware networks for crowd counting
• Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
• Multi-channel Deep Supervision for Crowd Counting
• Congestion Analysis of Convolutional Neural Network-Based Pedestrian Counting Methods on Helicopter Footage
• Towards Locally Consistent Object Counting with Constrained Multi-stage Convolutional Neural Networks
• Deep Crowd-Flow Prediction in Built Environments
• Weakly-supervised multi-class object localization using only object counts as labels